Navigate through Enigmatic Labyrinth A Survey of Chain of Thought Reasoning: Advances, Frontiers and Future

TL;DR

This survey comprehensively reviews recent advances in chain-of-thought reasoning for large language models, highlighting methods, challenges, and future directions to guide ongoing research in AI reasoning capabilities.

Contribution

It provides a systematic taxonomy of chain-of-thought reasoning methods, analyzes current frontiers, and discusses future challenges and open questions in the field.

Findings

Chain-of-thought prompting improves LLM reasoning performance.

A taxonomy categorizes recent methods and approaches.

Identifies key challenges and future research directions.

Abstract

Reasoning, a fundamental cognitive process integral to human intelligence, has garnered substantial interest within artificial intelligence. Notably, recent studies have revealed that chain-of-thought prompting significantly enhances LLM's reasoning capabilities, which attracts widespread attention from both academics and industry. In this paper, we systematically investigate relevant research, summarizing advanced methods through a meticulous taxonomy that offers novel perspectives. Moreover, we delve into the current frontiers and delineate the challenges and future directions, thereby shedding light on future research. Furthermore, we engage in a discussion about open questions. We hope this paper serves as an introduction for beginners and fosters future research. Resources have been made publicly available at https://github.com/zchuz/CoT-Reasoning-Survey